Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer
An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for...
Ausführliche Beschreibung
Autor*in: |
Nguon, Leang Sim [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2022transfer abstract |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
Enthalten in: Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion - Chae, Sukbyung ELSEVIER, 2017transfer abstract, the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society, Amsterdam [u.a.] |
---|---|
Übergeordnetes Werk: |
volume:98 ; year:2022 ; pages:0 |
Links: |
---|
DOI / URN: |
10.1016/j.compmedimag.2022.102073 |
---|
Katalog-ID: |
ELV057799644 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV057799644 | ||
003 | DE-627 | ||
005 | 20230626045759.0 | ||
007 | cr uuu---uuuuu | ||
008 | 220808s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.compmedimag.2022.102073 |2 doi | |
028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica |
035 | |a (DE-627)ELV057799644 | ||
035 | |a (ELSEVIER)S0895-6111(22)00046-5 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 660 |q VZ |
082 | 0 | 4 | |a 630 |a 640 |a 580 |q VZ |
084 | |a BIODIV |q DE-30 |2 fid | ||
084 | |a 42.00 |2 bkl | ||
100 | 1 | |a Nguon, Leang Sim |e verfasserin |4 aut | |
245 | 1 | 0 | |a Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer |
264 | 1 | |c 2022transfer abstract | |
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a nicht spezifiziert |b z |2 rdamedia | ||
338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
520 | |a An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. | ||
520 | |a An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. | ||
650 | 7 | |a Deep learning |2 Elsevier | |
650 | 7 | |a Reconstruction |2 Elsevier | |
650 | 7 | |a Beamforming |2 Elsevier | |
650 | 7 | |a Delay-and-sum |2 Elsevier | |
650 | 7 | |a Coherent plane-wave compounding |2 Elsevier | |
650 | 7 | |a Plane-wave ultrasound imaging |2 Elsevier | |
700 | 1 | |a Seo, Jungwung |4 oth | |
700 | 1 | |a Seo, Kangwon |4 oth | |
700 | 1 | |a Han, Yeji |4 oth | |
700 | 1 | |a Park, Suhyun |4 oth | |
773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Chae, Sukbyung ELSEVIER |t Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion |d 2017transfer abstract |d the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society |g Amsterdam [u.a.] |w (DE-627)ELV015598136 |
773 | 1 | 8 | |g volume:98 |g year:2022 |g pages:0 |
856 | 4 | 0 | |u https://doi.org/10.1016/j.compmedimag.2022.102073 |3 Volltext |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
912 | |a FID-BIODIV | ||
936 | b | k | |a 42.00 |j Biologie: Allgemeines |q VZ |
951 | |a AR | ||
952 | |d 98 |j 2022 |h 0 |
author_variant |
l s n ls lsn |
---|---|
matchkey_str |
nguonleangsimseojungwungseokangwonhanyej:2022----:eosrcinopaeaelrsudmgnuigoii |
hierarchy_sort_str |
2022transfer abstract |
bklnumber |
42.00 |
publishDate |
2022 |
allfields |
10.1016/j.compmedimag.2022.102073 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica (DE-627)ELV057799644 (ELSEVIER)S0895-6111(22)00046-5 DE-627 ger DE-627 rakwb eng 660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl Nguon, Leang Sim verfasserin aut Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Elsevier Seo, Jungwung oth Seo, Kangwon oth Han, Yeji oth Park, Suhyun oth Enthalten in Elsevier Science Chae, Sukbyung ELSEVIER Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion 2017transfer abstract the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society Amsterdam [u.a.] (DE-627)ELV015598136 volume:98 year:2022 pages:0 https://doi.org/10.1016/j.compmedimag.2022.102073 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV 42.00 Biologie: Allgemeines VZ AR 98 2022 0 |
spelling |
10.1016/j.compmedimag.2022.102073 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica (DE-627)ELV057799644 (ELSEVIER)S0895-6111(22)00046-5 DE-627 ger DE-627 rakwb eng 660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl Nguon, Leang Sim verfasserin aut Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Elsevier Seo, Jungwung oth Seo, Kangwon oth Han, Yeji oth Park, Suhyun oth Enthalten in Elsevier Science Chae, Sukbyung ELSEVIER Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion 2017transfer abstract the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society Amsterdam [u.a.] (DE-627)ELV015598136 volume:98 year:2022 pages:0 https://doi.org/10.1016/j.compmedimag.2022.102073 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV 42.00 Biologie: Allgemeines VZ AR 98 2022 0 |
allfields_unstemmed |
10.1016/j.compmedimag.2022.102073 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica (DE-627)ELV057799644 (ELSEVIER)S0895-6111(22)00046-5 DE-627 ger DE-627 rakwb eng 660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl Nguon, Leang Sim verfasserin aut Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Elsevier Seo, Jungwung oth Seo, Kangwon oth Han, Yeji oth Park, Suhyun oth Enthalten in Elsevier Science Chae, Sukbyung ELSEVIER Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion 2017transfer abstract the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society Amsterdam [u.a.] (DE-627)ELV015598136 volume:98 year:2022 pages:0 https://doi.org/10.1016/j.compmedimag.2022.102073 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV 42.00 Biologie: Allgemeines VZ AR 98 2022 0 |
allfieldsGer |
10.1016/j.compmedimag.2022.102073 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica (DE-627)ELV057799644 (ELSEVIER)S0895-6111(22)00046-5 DE-627 ger DE-627 rakwb eng 660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl Nguon, Leang Sim verfasserin aut Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Elsevier Seo, Jungwung oth Seo, Kangwon oth Han, Yeji oth Park, Suhyun oth Enthalten in Elsevier Science Chae, Sukbyung ELSEVIER Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion 2017transfer abstract the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society Amsterdam [u.a.] (DE-627)ELV015598136 volume:98 year:2022 pages:0 https://doi.org/10.1016/j.compmedimag.2022.102073 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV 42.00 Biologie: Allgemeines VZ AR 98 2022 0 |
allfieldsSound |
10.1016/j.compmedimag.2022.102073 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica (DE-627)ELV057799644 (ELSEVIER)S0895-6111(22)00046-5 DE-627 ger DE-627 rakwb eng 660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl Nguon, Leang Sim verfasserin aut Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Elsevier Seo, Jungwung oth Seo, Kangwon oth Han, Yeji oth Park, Suhyun oth Enthalten in Elsevier Science Chae, Sukbyung ELSEVIER Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion 2017transfer abstract the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society Amsterdam [u.a.] (DE-627)ELV015598136 volume:98 year:2022 pages:0 https://doi.org/10.1016/j.compmedimag.2022.102073 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV 42.00 Biologie: Allgemeines VZ AR 98 2022 0 |
language |
English |
source |
Enthalten in Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion Amsterdam [u.a.] volume:98 year:2022 pages:0 |
sourceStr |
Enthalten in Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion Amsterdam [u.a.] volume:98 year:2022 pages:0 |
format_phy_str_mv |
Article |
bklname |
Biologie: Allgemeines |
institution |
findex.gbv.de |
topic_facet |
Deep learning Reconstruction Beamforming Delay-and-sum Coherent plane-wave compounding Plane-wave ultrasound imaging |
dewey-raw |
660 |
isfreeaccess_bool |
false |
container_title |
Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion |
authorswithroles_txt_mv |
Nguon, Leang Sim @@aut@@ Seo, Jungwung @@oth@@ Seo, Kangwon @@oth@@ Han, Yeji @@oth@@ Park, Suhyun @@oth@@ |
publishDateDaySort_date |
2022-01-01T00:00:00Z |
hierarchy_top_id |
ELV015598136 |
dewey-sort |
3660 |
id |
ELV057799644 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV057799644</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626045759.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220808s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.compmedimag.2022.102073</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV057799644</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0895-6111(22)00046-5</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">630</subfield><subfield code="a">640</subfield><subfield code="a">580</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Nguon, Leang Sim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Deep learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Reconstruction</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Beamforming</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Delay-and-sum</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Coherent plane-wave compounding</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Plane-wave ultrasound imaging</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Jungwung</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Kangwon</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, Yeji</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Park, Suhyun</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Chae, Sukbyung ELSEVIER</subfield><subfield code="t">Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion</subfield><subfield code="d">2017transfer abstract</subfield><subfield code="d">the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV015598136</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:98</subfield><subfield code="g">year:2022</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.compmedimag.2022.102073</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.00</subfield><subfield code="j">Biologie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">98</subfield><subfield code="j">2022</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
author |
Nguon, Leang Sim |
spellingShingle |
Nguon, Leang Sim ddc 660 ddc 630 fid BIODIV bkl 42.00 Elsevier Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer |
authorStr |
Nguon, Leang Sim |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV015598136 |
format |
electronic Article |
dewey-ones |
660 - Chemical engineering 630 - Agriculture & related technologies 640 - Home & family management 580 - Plants (Botany) |
delete_txt_mv |
keep |
author_role |
aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging Elsevier |
topic |
ddc 660 ddc 630 fid BIODIV bkl 42.00 Elsevier Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging |
topic_unstemmed |
ddc 660 ddc 630 fid BIODIV bkl 42.00 Elsevier Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging |
topic_browse |
ddc 660 ddc 630 fid BIODIV bkl 42.00 Elsevier Deep learning Elsevier Reconstruction Elsevier Beamforming Elsevier Delay-and-sum Elsevier Coherent plane-wave compounding Elsevier Plane-wave ultrasound imaging |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
zu |
author2_variant |
j s js k s ks y h yh s p sp |
hierarchy_parent_title |
Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion |
hierarchy_parent_id |
ELV015598136 |
dewey-tens |
660 - Chemical engineering 630 - Agriculture 640 - Home & family management 580 - Plants (Botany) |
hierarchy_top_title |
Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)ELV015598136 |
title |
Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer |
ctrlnum |
(DE-627)ELV057799644 (ELSEVIER)S0895-6111(22)00046-5 |
title_full |
Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer |
author_sort |
Nguon, Leang Sim |
journal |
Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion |
journalStr |
Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
600 - Technology 500 - Science |
recordtype |
marc |
publishDateSort |
2022 |
contenttype_str_mv |
zzz |
container_start_page |
0 |
author_browse |
Nguon, Leang Sim |
container_volume |
98 |
class |
660 VZ 630 640 580 VZ BIODIV DE-30 fid 42.00 bkl |
format_se |
Elektronische Aufsätze |
author-letter |
Nguon, Leang Sim |
doi_str_mv |
10.1016/j.compmedimag.2022.102073 |
dewey-full |
660 630 640 580 |
title_sort |
reconstruction for plane-wave ultrasound imaging using modified u-net-based beamformer |
title_auth |
Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer |
abstract |
An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. |
abstractGer |
An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. |
abstract_unstemmed |
An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV |
title_short |
Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer |
url |
https://doi.org/10.1016/j.compmedimag.2022.102073 |
remote_bool |
true |
author2 |
Seo, Jungwung Seo, Kangwon Han, Yeji Park, Suhyun |
author2Str |
Seo, Jungwung Seo, Kangwon Han, Yeji Park, Suhyun |
ppnlink |
ELV015598136 |
mediatype_str_mv |
z |
isOA_txt |
false |
hochschulschrift_bool |
false |
author2_role |
oth oth oth oth |
doi_str |
10.1016/j.compmedimag.2022.102073 |
up_date |
2024-07-06T17:12:04.239Z |
_version_ |
1803850533299027968 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV057799644</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626045759.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">220808s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.compmedimag.2022.102073</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001781.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV057799644</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0895-6111(22)00046-5</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">630</subfield><subfield code="a">640</subfield><subfield code="a">580</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Nguon, Leang Sim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Reconstruction for plane-wave ultrasound imaging using modified U-Net-based beamformer</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">An image reconstruction method that can simultaneously provide high image quality and frame rate is necessary for diagnosis on cardiovascular imaging but is challenging for plane-wave ultrasound imaging. To overcome this challenge, an end-to-end ultrasound image reconstruction method is proposed for reconstructing a high-resolution B-mode image from radio frequency (RF) data. A modified U-Net architecture that adopts EfficientNet-B5 and U-Net as the encoder and decoder parts, respectively, is proposed as a deep learning beamformer. The training data comprise pairs of pre-beamformed RF data generated from random scatterers with random amplitudes and corresponding high-resolution target data generated from coherent plane-wave compounding (CPWC). To evaluate the performance of the proposed beamforming model, simulation and experimental data are used for various beamformers, such as delay-and-sum (DAS), CPWC, and other deep learning beamformers, including U-Net and EfficientNet-B0. Compared with single plane-wave imaging with DAS, the proposed beamforming model reduces the lateral full width at half maximum by 35% for simulation and 29.6% for experimental data and improves the contrast-to-noise ratio and peak signal-to-noise ratio, respectively, by 6.3 and 9.97 dB for simulation, 2.38 and 3.01 dB for experimental data, and 3.18 and 1.03 dB for in vivo data. Furthermore, the computational complexity of the proposed beamforming model is four times less than that of the U-Net beamformer. The study results demonstrate that the proposed ultrasound image reconstruction method employing a deep learning beamformer, trained by the RF data from scatterers, can reconstruct a high-resolution image with a high frame rate for single plane-wave ultrasound imaging.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Deep learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Reconstruction</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Beamforming</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Delay-and-sum</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Coherent plane-wave compounding</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Plane-wave ultrasound imaging</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Jungwung</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Seo, Kangwon</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Han, Yeji</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Park, Suhyun</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Chae, Sukbyung ELSEVIER</subfield><subfield code="t">Synthesis of terraced and spherical MgO nanoparticles using flame metal combustion</subfield><subfield code="d">2017transfer abstract</subfield><subfield code="d">the international journal on imaging and image-archiving in all medical specialties : the official journal of the Computerized Medical Image Society</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV015598136</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:98</subfield><subfield code="g">year:2022</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.compmedimag.2022.102073</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.00</subfield><subfield code="j">Biologie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">98</subfield><subfield code="j">2022</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
score |
7.399722 |